Python:

import requests
from bs4 import BeautifulSoup

url = 'http://top.baidu.com/buzz?b=1&fr=topbuzz_b1'
save_path = 'hot_python.txt'

if __name__ == '__main__':
    content = requests.get(url).content
    soup = BeautifulSoup(content, 'lxml')
    items = soup.select('table.list-table > tr > .keyword > .list-title')

    with open(save_path, 'w') as f:
        f.writelines('')

    for item in items:
        with open(save_path, 'a') as f:
            f.writelines(item.text + '\n')

Java:

需引用maven库：

<dependency>
   <groupId>org.jsoup</groupId>
   <artifactId>jsoup</artifactId>
   <version>1.11.3</version>
</dependency>

爬虫代码：

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.io.BufferedWriter;
import java.io.File;
import java.io.FileWriter;
import java.io.IOException;

public class BaiduHotSpider {

    private static final String URL = "http://top.baidu.com/buzz?b=1&fr=topbuzz_b1";
    private static final String SAVE_PATH = "hot_java.txt";

    public static void main(String args[]) throws IOException {
        Document document = Jsoup.connect(URL).get();
        Elements elements = document.select("table.list-table > tbody > tr > .keyword > .list-title");

        File file = new File(SAVE_PATH);
        if(file.exists()){
            file.delete();
        }
        file.createNewFile();

        FileWriter fw = new FileWriter(file.getAbsoluteFile(),true);
        BufferedWriter bw = new BufferedWriter(fw);
        for(Element element : elements){
            bw.write(element.text() + "\n");
        }
        bw.close();
    }
}